mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-26 04:25:18 +07:00
b99afae139
The naked attribute is known to confuse some old gcc versions when
function arguments aren't explicitly listed as inline assembly operands
despite the gcc documentation. That resulted in commit 9a40ac8615
("ARM: 6164/1: Add kto and kfrom to input operands list.").
Yet that commit has problems of its own by having assembly operand
constraints completely wrong. If the generated code has been OK since
then, it is due to luck rather than correctness. So this patch also
provides proper assembly operand constraints, and removes two instances
of redundant register usages in the implementation while at it.
Inspection of the generated code with this patch doesn't show any
obvious quality degradation either, so not relying on __naked at all
will make the code less fragile, and avoid some issues with clang.
The only remaining __naked instances (excluding the kprobes test cases)
are exynos_pm_power_up_setup(), tc2_pm_power_up_setup() and
cci_enable_port_for_self(. But in the first two cases, only the function
address is used by the compiler with no chance of inlining it by
mistake, and the third case is called from assembly code only. And the
fact that no stack is available when the corresponding code is executed
does warrant the __naked usage in those cases.
Signed-off-by: Nicolas Pitre <nico@linaro.org>
Reviewed-by: Stefan Agner <stefan@agner.ch>
Tested-by: Stefan Agner <stefan@agner.ch>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
111 lines
3.2 KiB
C
111 lines
3.2 KiB
C
/*
|
|
* linux/arch/arm/mm/copypage-feroceon.S
|
|
*
|
|
* Copyright (C) 2008 Marvell Semiconductors
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
* published by the Free Software Foundation.
|
|
*
|
|
* This handles copy_user_highpage and clear_user_page on Feroceon
|
|
* more optimally than the generic implementations.
|
|
*/
|
|
#include <linux/init.h>
|
|
#include <linux/highmem.h>
|
|
|
|
static void feroceon_copy_user_page(void *kto, const void *kfrom)
|
|
{
|
|
int tmp;
|
|
|
|
asm volatile ("\
|
|
1: ldmia %1!, {r2 - r7, ip, lr} \n\
|
|
pld [%1, #0] \n\
|
|
pld [%1, #32] \n\
|
|
pld [%1, #64] \n\
|
|
pld [%1, #96] \n\
|
|
pld [%1, #128] \n\
|
|
pld [%1, #160] \n\
|
|
pld [%1, #192] \n\
|
|
stmia %0, {r2 - r7, ip, lr} \n\
|
|
ldmia %1!, {r2 - r7, ip, lr} \n\
|
|
mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add %0, %0, #32 \n\
|
|
stmia %0, {r2 - r7, ip, lr} \n\
|
|
ldmia %1!, {r2 - r7, ip, lr} \n\
|
|
mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add %0, %0, #32 \n\
|
|
stmia %0, {r2 - r7, ip, lr} \n\
|
|
ldmia %1!, {r2 - r7, ip, lr} \n\
|
|
mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add %0, %0, #32 \n\
|
|
stmia %0, {r2 - r7, ip, lr} \n\
|
|
ldmia %1!, {r2 - r7, ip, lr} \n\
|
|
mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add %0, %0, #32 \n\
|
|
stmia %0, {r2 - r7, ip, lr} \n\
|
|
ldmia %1!, {r2 - r7, ip, lr} \n\
|
|
mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add %0, %0, #32 \n\
|
|
stmia %0, {r2 - r7, ip, lr} \n\
|
|
ldmia %1!, {r2 - r7, ip, lr} \n\
|
|
mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add %0, %0, #32 \n\
|
|
stmia %0, {r2 - r7, ip, lr} \n\
|
|
ldmia %1!, {r2 - r7, ip, lr} \n\
|
|
mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add %0, %0, #32 \n\
|
|
stmia %0, {r2 - r7, ip, lr} \n\
|
|
subs %2, %2, #(32 * 8) \n\
|
|
mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add %0, %0, #32 \n\
|
|
bne 1b \n\
|
|
mcr p15, 0, %2, c7, c10, 4 @ drain WB"
|
|
: "+&r" (kto), "+&r" (kfrom), "=&r" (tmp)
|
|
: "2" (PAGE_SIZE)
|
|
: "r2", "r3", "r4", "r5", "r6", "r7", "ip", "lr");
|
|
}
|
|
|
|
void feroceon_copy_user_highpage(struct page *to, struct page *from,
|
|
unsigned long vaddr, struct vm_area_struct *vma)
|
|
{
|
|
void *kto, *kfrom;
|
|
|
|
kto = kmap_atomic(to);
|
|
kfrom = kmap_atomic(from);
|
|
flush_cache_page(vma, vaddr, page_to_pfn(from));
|
|
feroceon_copy_user_page(kto, kfrom);
|
|
kunmap_atomic(kfrom);
|
|
kunmap_atomic(kto);
|
|
}
|
|
|
|
void feroceon_clear_user_highpage(struct page *page, unsigned long vaddr)
|
|
{
|
|
void *ptr, *kaddr = kmap_atomic(page);
|
|
asm volatile ("\
|
|
mov r1, %2 \n\
|
|
mov r2, #0 \n\
|
|
mov r3, #0 \n\
|
|
mov r4, #0 \n\
|
|
mov r5, #0 \n\
|
|
mov r6, #0 \n\
|
|
mov r7, #0 \n\
|
|
mov ip, #0 \n\
|
|
mov lr, #0 \n\
|
|
1: stmia %0, {r2-r7, ip, lr} \n\
|
|
subs r1, r1, #1 \n\
|
|
mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\
|
|
add %0, %0, #32 \n\
|
|
bne 1b \n\
|
|
mcr p15, 0, r1, c7, c10, 4 @ drain WB"
|
|
: "=r" (ptr)
|
|
: "0" (kaddr), "I" (PAGE_SIZE / 32)
|
|
: "r1", "r2", "r3", "r4", "r5", "r6", "r7", "ip", "lr");
|
|
kunmap_atomic(kaddr);
|
|
}
|
|
|
|
struct cpu_user_fns feroceon_user_fns __initdata = {
|
|
.cpu_clear_user_highpage = feroceon_clear_user_highpage,
|
|
.cpu_copy_user_highpage = feroceon_copy_user_highpage,
|
|
};
|
|
|